Determination of the descriptors for the design of a classifier that allows the detection of loss of material in metal sheets based on signals of non-destructive tests

Hernando Gonzalez, Carlos Arizmendi, Javier Quintero, Mario A. Quintero

Resultado de la investigación: Libro / Capitulo del libro / InformeLibros de Investigaciónrevisión exhaustiva

Resumen

The article proposes a methodology to determine appropriate descriptors for the design of a classifier based on neural networks that allow the detection of loss of material in metal pipes based on nondestructive testing signals of Magnetic Flux Leakage (MFL). For this it has been proposed a method which consists of two stages: the first, corresponding to the signal processing, the Discrete Wavelet Transform (DWT) transform is used to implement a nonlinear threshold filtering or Shrinkage and correction baseline which seeks to eliminate or mitigate the different types of noise or phenomena found in the signal that make difficult the process of extracting relevant information to the subsequent detection of loss of material. In the second, corresponding to the design of the classifier, it seeks to identify a window width and descriptors in the time domain and the Power Spectral Density (PSD) to characterize the signal and differentiate areas of metal loss or no metal loss.

Idioma originalInglés
Título de la publicación alojada2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas122-127
Número de páginas6
ISBN (versión digital)9781538669877
DOI
EstadoPublicada - 25 jun. 2018
Evento2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018 - Chengdu, China
Duración: 26 may. 201828 may. 2018

Serie de la publicación

Nombre2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018

Conferencia

Conferencia2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018
País/TerritorioChina
CiudadChengdu
Período26/05/1828/05/18

Huella

Profundice en los temas de investigación de 'Determination of the descriptors for the design of a classifier that allows the detection of loss of material in metal sheets based on signals of non-destructive tests'. En conjunto forman una huella única.

Citar esto